pokemon

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). At runtime the skill calls PokéAPI (public web content) to fetch Pokémon/type/ability data, and that fetched free-text fields are ingested into the agent’s LLM context as the command output.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)